WO2018053977A1 - 一种图像补偿方法和装置 - Google Patents

一种图像补偿方法和装置 Download PDF

Info

Publication number
WO2018053977A1
WO2018053977A1 PCT/CN2017/071360 CN2017071360W WO2018053977A1 WO 2018053977 A1 WO2018053977 A1 WO 2018053977A1 CN 2017071360 W CN2017071360 W CN 2017071360W WO 2018053977 A1 WO2018053977 A1 WO 2018053977A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
window
valid
background
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2017/071360
Other languages
English (en)
French (fr)
Inventor
邱新华
陈春光
刘梦涛
王荣秋
王卫锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GRG Banking Equipment Co Ltd
Intellicash Equipment Co Ltd
Original Assignee
GRG Banking Equipment Co Ltd
Intellicash Equipment Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by GRG Banking Equipment Co Ltd, Intellicash Equipment Co Ltd filed Critical GRG Banking Equipment Co Ltd
Publication of WO2018053977A1 publication Critical patent/WO2018053977A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/14—Picture signal circuitry for video frequency region
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/14—Picture signal circuitry for video frequency region
    • H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo

Definitions

  • the present invention relates to the field of image processing, and in particular, to an image compensation method and apparatus.
  • Line scanning sensors such as CIS (Contact Image Sensor) are widely used in scanners and intelligent identification instruments.
  • the temperature environment of the sensor is different, and the aging of the sensor causes the characteristic curve to change over time.
  • the actual signal collected is greatly deviated from the ideal situation, such as between the sensor parts. Chip line. If it occurs in the banknote identification system, it will cause batch misidentification, which greatly reduces the reliability of the system; if it occurs in the scanning instrument, the image will be distorted and unacceptable. Therefore, it is of great significance to ensure the quality of the signals collected in different environments.
  • the most commonly used is to obtain the compensation coefficient of the image at different positions through the calibration paper in advance, and save the compensation coefficient of different positions and the compensation coefficient at different temperatures in the memory, and firstly pass the temperature and other sensors when collecting the signal.
  • the current environment is acquired, and then the compensation coefficient is compensated according to the compensation coefficient in different temperature environments of the saved respective positions, thereby determining the compensation coefficient in which temperature environment is used.
  • the existing technology not only requires a lot of memory to store these compensation coefficients, but also requires an additional temperature sensor, which increases system cost and operation difficulty.
  • the embodiment of the invention provides an image compensation method and device, which calculates the background value of the original signal by determining the effective window and the effective signal, and then calculates the compensation value of the original signal, finally determines and outputs the compensation signal, and solves the existing technology.
  • a lot of memory is needed to save the compensation factor, and an additional temperature sensor is needed, which increases the technical cost of the system and the technical difficulty of operation.
  • An embodiment of the present invention provides an image compensation method, including:
  • Determining the effective window according to the preset parameter calculation window determined by the original signal of the acquired scanned image, and calculating a valid signal corresponding to each valid window according to the determined valid window specifically:
  • the parameter calculating window is a valid window, otherwise it is an invalid window
  • a signal in the valid window that is within the resampling threshold range is determined to be a valid signal, otherwise an invalid signal.
  • the background values of each column of the original signal are summed and then divided by the width of the preset parameter calculation window, and the resulting quotient is taken as the background reference value for the entire original signal.
  • Subtracting the background signal of the entire signal from the background value of the original signal indicates the compensation value of the column
  • the compensation value of each column is summed with all the signals in the same column to obtain a compensation signal, and the compensated signal is output.
  • An embodiment of the present invention provides an image compensation apparatus, including:
  • An effective signal determining unit configured to determine a valid window according to the preset parameter calculation window determined by the original signal of the acquired scanned image, and calculate a valid signal corresponding to each of the valid windows according to the determined valid window;
  • a background value unit configured to perform calculation of a background value corresponding to the original signal according to the calculated valid signal
  • a background reference value unit performing calculation of a background reference value of the original signal according to the background value and the information of the preset parameter calculation window;
  • a compensation signal unit configured to determine a compensation signal corresponding to the original signal according to the background reference value and the background value.
  • the valid signal determining unit includes an initializing subunit, a resampling threshold calculating subunit, a valid window determining subunit, and a valid signal determining subunit;
  • the initialization subunit is configured to acquire an original signal of the scanned image, and create and initialize a parameter calculation window;
  • the resampling threshold calculating subunit is configured to calculate a resampling threshold by using a data amount included in all gray levels of the parameter calculation window and a proportion of the data amount in the parameter calculating window;
  • the valid window determining subunit is configured to determine the resampling threshold. If the resampling threshold is within a preset range, the parameter calculating window is a valid window, otherwise it is an invalid window;
  • the valid signal determining subunit is configured to determine that the signal in the valid window within the resampling threshold range is a valid signal, otherwise it is an invalid signal.
  • the background value unit includes a valid signal calculation subunit and a background value calculation subunit
  • the effective signal calculation subunit is configured to obtain the number of valid signals per column of each valid window and the accumulated sum of valid signals of each column;
  • the background value calculation sub-unit is configured to calculate a sum of the summation of the same column valid signals in each valid window, and then divide by the sum of the number of valid signals in the same column in each valid window, and the quotient represents the background value of the column of the original signal.
  • the background reference value unit is specifically configured to sum the background values of each column of the original signal and then divide by the width of the preset parameter calculation window, and obtain the obtained quotient as the background reference value of the entire original signal. .
  • the compensation signal unit includes a compensation value calculation subunit and a compensation signal output subunit;
  • the compensation value calculation subunit is configured to subtract the background reference value of the entire signal from the background value of the original signal to represent the compensation value of the column;
  • the compensation signal output subunit is configured to sum up the compensation value of each column and all the signals in the same column to obtain a compensation signal, and output the compensated signal.
  • FIG. 1 is a flowchart of a first embodiment of an image compensation method according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a second embodiment of an image compensation method according to an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of an example of a normal sample of an image compensation method according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of an example of an abnormal sample of an image compensation method according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a parameter calculation window of an image compensation method according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of comparing an estimated gray scale distribution with a reference value according to an image compensation method according to an embodiment of the present invention
  • FIG. 7 is a schematic diagram of a sample after successful compensation of an image compensation method according to an embodiment of the present invention.
  • FIG. 8 is a structural diagram of a first embodiment of an image compensation apparatus based on an image compensation method according to an embodiment of the present invention.
  • FIG. 9 is a structural diagram of a second embodiment of an image compensation apparatus based on an image compensation method according to an embodiment of the present invention.
  • the embodiment of the invention provides an image compensation method and device, which calculates the background value of the original signal by determining the effective window and the effective signal, and then calculates the compensation value of the original signal, finally determines and outputs the compensation signal, and solves the existing technology.
  • a lot of memory is needed to save the compensation factor, and an additional temperature sensor is needed, which increases the technical cost of the system and the technical difficulty of operation.
  • a first embodiment of an image compensation method according to an embodiment of the present invention includes:
  • the preset determined according to the original signal of the acquired scanned image is first required.
  • the parameter calculation window determines the effective window, and calculates a valid signal corresponding to each valid window according to the determined effective window.
  • the original signal needs to be original according to the calculated valid signal.
  • the calculation of the background value corresponding to the signal is performed according to the preset parameter calculation window determined by the original signal of the acquired scanned image, and the valid signal corresponding to each valid window is calculated according to the determined effective window.
  • the calculation of the background value corresponding to the original signal After the calculation of the background value corresponding to the original signal is performed according to the calculated valid signal, the calculation of the background reference value of the original signal needs to be performed according to the background value and the preset parameter calculation window.
  • FIG. 2 to FIG. 7 a second implementation of an image compensation method according to an embodiment of the present invention is provided. Examples include:
  • the resampling threshold After calculating the resampling threshold by the amount of data and the amount of data included in all the gray levels of the parameter calculation window in the parameter calculation window, the resampling threshold needs to be determined. If the resampling threshold is within the preset range, then The parameter calculation window is a valid window, otherwise it is an invalid window.
  • the re-sampling threshold is determined. If the re-sampling threshold is within the preset range, the parameter calculation window is a valid window. Otherwise, after the invalid window, it is necessary to determine that the signal in the re-sampling threshold range of the effective window is a valid signal. Otherwise it is an invalid signal.
  • the signal within the resampling threshold range is determined to be a valid signal in the determined effective window. Otherwise, after the invalid signal, it is necessary to obtain the number of valid signals per column of each valid window and the sum of the effective signals of each column.
  • the resulting quotient is used as the background reference value of the entire original signal, and the background reference value of the entire signal is subtracted from the original signal.
  • the column background value represents the compensation value for this column.
  • Subtracting the background signal of the entire signal from the background value of each column indicates the compensation value of the column. It is necessary to sum the compensation value of each column with all the signals in the same column to obtain a compensation signal, and output the compensated signal.
  • T i (S i,2 /S i,1 )-d (where d is set to 20) to obtain T i , and if T i satisfies the preset ratio range (100 ⁇ T i ⁇ 180), the parameter calculation window valid window, through the window and the weights ⁇ i flag is set, if T i does not satisfy the predetermined ratio range (100 ⁇ T i ⁇ 180), window invalid parameter calculation window, and a window through the weights ⁇ i flag set to 0
  • the black pixel of the gray histogram in WIN 2 accounts for 80% of the window, and the first S 2,1 >50% stops accumulating when S 2,1 is equal to 95%.
  • the calculated T 2 40, T 2 is not within the preset range, so ⁇ 2 is set to zero.
  • g i,r,c represents the signal value of the rth row and c column of WIN i ; when ⁇ i,r,c is 1, g i,r,c is the effective signal value, and vice versa is the invalid signal value; i, c represents the cumulative sum of the valid signal values in column c of WIN i .
  • the background reference value ref is calculated according to the formula (5), that is, the background reference value ref is averaged by the background value D c representing each column of the entire image, and the compensation value Cs c of the signal of the c-th column is calculated according to the equation (6).
  • the difference between the background value D c of each column and the background reference value ref can be used to represent the entire image of all pixels of the column.
  • the noise interference is the compensation value Cs c .
  • the calculated D c waveform is deviated from the background reference value ref to obtain a compensation value Cs c .
  • the ordinate represents the amplitude and the abscissa represents the column coordinates.
  • the compensation signal Cs c of each of the obtained signals is summed with the original signal value to obtain a compensation signal, such as equation (7), and the signal f(r, c) after the successful compensation is output, where g(r, c) is each position.
  • the original signal value is shown in Figure 7.
  • the original abnormal bright bars, dark bars, and chip lines can be eliminated, and the areas where there is no interference will not be affected.
  • an embodiment of the present invention further provides a first embodiment of an image compensation apparatus, including:
  • the effective signal determining unit 301 is configured to perform a determination of the effective window according to the preset parameter calculation window determined by the original signal of the acquired scanned image, and calculate a valid signal corresponding to each valid window according to the determined effective window;
  • the background value unit 302 is configured to perform calculation of a background value corresponding to the original signal according to the calculated valid signal
  • the background reference value unit 303 calculates the background reference value of the original signal according to the background value and the information of the preset parameter calculation window;
  • the compensation signal unit 304 determines the compensation signal corresponding to the original signal according to the background reference value and the background value.
  • an image compensating device provided in the embodiment of the present invention.
  • Two embodiments include:
  • the effective signal determining unit 401 is configured to determine the effective window according to the preset parameter calculation window determined by the original signal of the acquired scanned image, and calculate a valid signal corresponding to each valid window according to the determined effective window;
  • the background value unit 402 is configured to perform calculation of a background value corresponding to the original signal according to the calculated valid signal
  • the background reference value unit 403 calculates the background reference value of the original signal according to the background value and the preset parameter calculation window
  • the compensation signal unit 404 determines the compensation signal corresponding to the original signal according to the background reference value and the background value.
  • the valid signal determining unit 401 includes an initializing subunit 4011, a resampling threshold calculating subunit 4012, a valid window determining subunit 4013, and a valid signal determining subunit 4014;
  • the initialization subunit 4011 is configured to acquire an original signal of the scanned image, and create and initialize a parameter calculation window;
  • a resampling threshold calculation subunit 4012 configured to calculate a resampling threshold value by using a data amount and a data amount of all gray levels included in the parameter calculation window in a proportion of the parameter calculation window;
  • the valid window determining sub-unit 4013 is configured to determine the re-sampling threshold. If the re-sampling threshold is within the preset range, the parameter calculating window is a valid window, otherwise it is an invalid window;
  • the valid signal determining sub-unit 4014 is configured to determine that the signal in the effective window is within the resampling threshold range is a valid signal, otherwise it is an invalid signal.
  • the background value unit 402 includes a valid signal calculation subunit 4021 and a background value calculation subunit 4022;
  • the effective signal calculation sub-unit 4021 is configured to obtain the number of valid signals per column of each valid window and the accumulated sum of valid signals of each column;
  • the background value calculation sub-unit 4022 is configured to calculate a sum of the sum of the effective signals of the same column in each valid window, and then divide by the sum of the number of valid signals in the same column in each valid window, and the quotient represents the background value of the column of the original signal.
  • the background reference value unit 403 is specifically configured to sum the background values of each column of the original signal and then divide by the width of the preset parameter calculation window, and the derived quotient is used as the background reference value of the entire original signal.
  • the compensation signal unit 404 includes a compensation value calculation subunit 4041 and a compensation signal output subunit 4042;
  • the compensation value calculation subunit 4041 is configured to subtract the background reference value of the entire signal from the background value of the original signal to represent the compensation value of the column;
  • the compensation signal output sub-unit 4042 is configured to sum the compensation value of each column with all the signals in the same column to obtain a compensation signal, and output the compensated signal.
  • the initializing subunit 4011 first acquires the original signal of the scanned image, creates and initializes a parameter calculation window, and then the resampling threshold calculating subunit 4012 uses the data amount and the data amount included in all gray levels of the parameter calculation window in the parameter.
  • the ratio of the calculation window calculates the resampling threshold, and then the valid window determining subunit 4013 determines the resampling threshold.
  • the parameter calculating window is a valid window, otherwise it is an invalid window, and further The valid signal judging subunit 4014 determines that the signal in the effective window within the resampling threshold range is a valid signal, otherwise it is an invalid signal, and then the effective signal calculating subunit 4021 obtains the number of valid signals per column of each valid window and the effective signal of each column. Accumulating sum, the background value calculation sub-unit 4022 calculates the sum of the summations of the same column valid signals in the respective valid windows, and then divides the sum of the number of valid signals in the same column in each valid window, and represents the background value of the column of the original signal, the background reference value.
  • Unit 403 sums the background values of each column of the original signal and divides by the preset parameter calculation window. Width, the resulting quotient is taken as the background reference value of the whole original signal.
  • the compensation value calculation subunit 4041 subtracts the background value of the original signal from the background reference value of the entire signal to represent the compensation value of the column, and finally compensates the signal output subunit.
  • 4042 sums the compensation value of each column with all the signals in the same column to obtain a compensation signal, and outputs the compensated signal.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)

Abstract

本发明实施例公开了一种图像补偿方法和装置，通过确定有效窗和有效信号计算原始信号的背景值，进而计算出原始信号的补偿值，最终确定并输出补偿信号，解决了现有的技术需要很多存储器保存补偿系数，且需要额外的温度传感器，增加系统成本和操作难度的技术问题。本发明实施例方法包括：根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号；根据计算出的所述有效信号进行所述原始信号对应的背景值的计算；根据所述背景值与所述预置参数计算窗进行所述原始信号的背景参考值的计算；根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号。

Description

一种图像补偿方法和装置
本申请要求于2016年9月20日提交中国专利局、申请号为201610836702.2、发明名称为“一种图像补偿方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及图像处理领域，尤其涉及一种图像补偿方法和装置。
背景技术
CIS(Contact Image Sensor，接触式图像传感器)等线扫描传感器在扫描仪、智能清分识别仪器等领域中应用非常广泛。在不同的应用场景下，传感器所处的温度环境不同，以及随着时间的推移会引起传感器老化导致其特性曲线发生变化，所采集的实际信号与理想情况发生较大的偏差，如传感器件间的chip线。如果发生在钞票识别系统中，会引起批量误识别现象，极大程度上降低系统的可靠性；若发生在扫描仪器中，会导致图像失真而无法接受。因此，保证不同环境下采集的信号质量具有重大的意义。
现有的技术中，最常用的是预先通过校准纸获取图像在不同位置的补偿系数，并将不同位置的补偿系数和不同温度下的补偿系数保存在存储器中，采集信号时先通过温度等传感器获取当前环境，然后根据利用保存的各个位置的不同温度环境下的补偿系数补偿图像，从而决定使用哪种温度环境下的补偿系数。
然而，现有的技术不仅需要很多存储器保存这些补偿系数，且需要额外的温度传感器，增加系统成本和操作难度。
发明内容
本发明实施例提供了一种图像补偿方法和装置，通过确定有效窗和有效信号计算原始信号的背景值，进而计算出原始信号的补偿值，最终确定并输出补偿信号，解决了现有的技术需要很多存储器保存补偿系数，且需要额外的温度传感器，增加系统成本和操作难度的技术问题。
本发明实施例提供了一种图像补偿方法，包括：
根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号；
根据计算出的所述有效信号进行所述原始信号对应的背景值的计算；
根据所述背景值与所述预置参数计算窗的信息进行所述原始信号的背景参考值的计算；
根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号。
可选地，
根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号具体为：
获取扫描图像的原始信号，创建并初始化参数计算窗；
通过所述参数计算窗的所有灰度等级包含的数据量及所述数据量在所述参数计算窗的占比计算出重采样阈值；
对所述重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗；
确定所述有效窗中在所述重采样阈值范围内的信号为有效信号，否则为无效信号。
可选地，
根据计算出的所述有效信号进行所述原始信号对应的背景值的计算具体为：
获取各个有效窗每列有效信号的数目以及每列有效信号的累加和；
计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值。
可选地，
根据所述背景值与所述预置参数计算窗的信息进行所述原始信号的背景参考值的计算具体为：
将所述原始信号每列的所述背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个所述原始信号的背景参考值。
可选地，
根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号具体为：
用整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值；
将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
本发明实施例提供了一种图像补偿装置，包括：
有效信号确定单元，用于根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号；
背景值单元，用于根据计算出的所述有效信号进行所述原始信号对应的背景值的计算；
背景参考值单元，根据所述背景值与所述预置参数计算窗的信息进行所述原始信号的背景参考值的计算；
补偿信号单元，根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号。
可选地，
所述有效信号确定单元包括初始化子单元、重采样阈值计算子单元、有效窗判断子单元、有效信号判断子单元；
所述初始化子单元，用于获取扫描图像的原始信号，创建并初始化参数计算窗；
所述重采样阈值计算子单元，用于通过所述参数计算窗的所有灰度等级包含的数据量及所述数据量在所述参数计算窗的占比计算出重采样阈值；
所述有效窗判断子单元，用于对所述重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗；
所述有效信号判断子单元，用于确定所述有效窗中在所述重采样阈值范围内的信号为有效信号，否则为无效信号。
可选地，
所述背景值单元包括有效信号计算子单元和背景值计算子单元；
所述有效信号计算子单元，用于获取各个有效窗每列有效信号的数目以及每列有效信号的累加和；
背景值计算子单元，用于计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值。
可选地，
所述背景参考值单元具体用于将所述原始信号每列的所述背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个所述原始信号的背景参考值。
可选地，
所述补偿信号单元包括补偿值计算子单元和补偿信号输出子单元；
所述补偿值计算子单元，用于把整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值；
所述补偿信号输出子单元，用于将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
从以上技术方案可以看出，本发明实施例具有以下优点：
通过确定有效窗和有效信号计算原始信号的背景值，进而计算出原始信号的补偿值，最终确定并输出补偿信号，充分利用了线扫描传感器的特性和有效图像区域数据图像分布特性，不需要探测传感器所处环境的温度，解决了现有技术需要很多存储器保存补偿系数、需要额外的温度传感器、增加系统成本和操作难度的技术问题，进而使得补偿值的测定不受温度的影响，无论在高温、常温、低温环境下都能得到高质量无失真的图像信号；而且通过在线计算窗进行图像补偿值的计算，计算更新效率高，能适应复杂的背景。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其它的附图。
图1为本发明实施例提供的一种图像补偿方法的第一个实施例的流程图；
图2为本发明实施例提供的一种图像补偿方法的第二个实施例的流程图；
图3为本发明实施例提供的一种图像补偿方法的正常样本示例的示意图；
图4为本发明实施例提供的一种图像补偿方法的异常样本示例的示意图；
图5为本发明实施例提供的一种图像补偿方法的参数计算窗示意图；
图6为本发明实施例提供的一种图像补偿方法的估计灰度分布与参考值对比示意图；
图7为本发明实施例提供的一种图像补偿方法的补偿成功后的样本示意图；
图8为本发明实施例提供的一种基于图像补偿方法的图像补偿装置的第一个实施例的结构图；
图9为本发明实施例提供的一种基于图像补偿方法的图像补偿装置的第二个实施例的结构图。
具体实施方式
本发明实施例提供了一种图像补偿方法和装置，通过确定有效窗和有效信号计算原始信号的背景值，进而计算出原始信号的补偿值，最终确定并输出补偿信号，解决了现有的技术需要很多存储器保存补偿系数，且需要额外的温度传感器，增加系统成本和操作难度的技术问题。
为使得本发明的发明目的、特征、优点能够更加的明显和易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，下面所描述的实施例仅仅是本发明一部分实施例，而非全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
请参阅图1、图3至图7，本发明实施例提供的一种图像补偿方法的第一个实施例包括：
101，根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的有效窗计算出各有效窗对应的有效信号；
在本实施例中，首先需要根据获取到的扫描图像的原始信号所确定的预置 参数计算窗进行有效窗的确定，并根据确定的有效窗计算出各有效窗对应的有效信号。
102，根据计算出的有效信号进行原始信号对应的背景值的计算；
当根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的有效窗计算出各有效窗对应的有效信号之后，需要根据计算出的有效信号进行原始信号对应的背景值的计算。
103，根据背景值与预置参数计算窗的信息进行原始信号的背景参考值的计算；
当根据计算出的有效信号进行原始信号对应的背景值的计算之后，需要根据背景值与预置参数计算窗进行原始信号的背景参考值的计算。
104，根据背景参考值与背景值确定原始信号对应的补偿信号；
当根据背景值与预置参数计算窗进行原始信号的背景参考值的计算之后，需要根据背景参考值与背景值确定原始信号对应的补偿信号。
上面是对图像补偿方法的过程进行的描述，下面将对图像补偿方法的过程进行详细的描述，请参阅图图2至图7，本发明实施例提供的一种图像补偿方法的第二个实施例包括：
201，获取扫描图像的原始信号，创建并初始化参数计算窗；
在本实施例中，首先需要获取扫描图像的原始信号，创建并初始化参数计算窗。
202，通过参数计算窗的所有灰度等级包含的数据量及数据量在参数计算窗的占比计算出重采样阈值；
在获取扫描图像的原始信号，创建并初始化参数计算窗之后，需要通过参数计算窗的所有灰度等级包含的数据量及数据量在参数计算窗的占比计算出重采样阈值。
203，对重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗；
在通过参数计算窗的所有灰度等级包含的数据量及数据量在参数计算窗的占比计算出重采样阈值之后，需要对重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗。
204，确定有效窗中在重采样阈值范围内的信号为有效信号，否则为无效信号；
在对重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗之后，需要确定有效窗中在重采样阈值范围内的信号为有效信号，否则为无效信号。
205，获取各个有效窗每列有效信号的数目以及每列有效信号的累加和；
在确定有效窗中在重采样阈值范围内的信号为有效信号，否则为无效信号之后，需要获取各个有效窗每列有效信号的数目以及每列有效信号的累加和。
206，计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值；
在获取各个有效窗每列有效信号的数目以及每列有效信号的累加和之后，需要计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值。
207，将原始信号每列的背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个原始信号的背景参考值；
在计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值之后，需要将原始信号每列的背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个原始信号的背景参考值。
208，用整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值；
在将原始信号每列的背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个原始信号的背景参考值之后，需要整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值。
209，将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号；
在用整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值，需要将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
需要说明的是，根据所获取的原始扫描信号的宽、高等信息创建并初始化参数计算窗WINi,(i＝0,1,2,…n)，参数计算窗WINi的位置信息包括左上顶点Pti(xi,yi),Wi和Hi，如图5所示参数计算窗；
然后计算参数计算窗WINi中所有灰度等级包含的数据量Gi,j,(j＝0,1,2…255)及其在WINi中所占的比例Ratei,j，其中：Ratei,j＝Gi,j/(Wi*Hi)。根据Gi,j和Ratei,j计算得出重采样阈值Ti；例如，在WINi中，将j＝255自减1一直到0时累加Ratei,j得到累加比例和Si,1，同时累加(Gi,j*Ratei,j)得到累加灰度和Si,2，当累加比例和Si,1满足预设比例范围(大于50％)范围则停止累加，此时通过Ti＝(Si,2/Si,1)-d(此处d设为20)求取Ti，若Ti满足预设比例范围(100≤Ti≤180)，则参数计算窗为有效窗，并通过将窗权重ωi置1标记，若Ti不满足预设比例范围(100≤Ti≤180)，参数计算窗为无效窗，并通过将窗权重ωi置0标记；如图5所示3个参数计算窗中，假设WIN2中灰度直方图黑色像素占该窗的80％，首次S2,1>50％停止累加时S2,1等于95％，所计算得到的T2＝40，T2不在预设范围内，故将ω2置为0。
按式(1)、(2)计算每个WINi中的同列有效信号累加和li,c，(Pti(xi)≤c＜Wi)，此处假设各个参数计算窗的宽Wi相等；
Figure PCTCN2017071360-appb-000001
Figure PCTCN2017071360-appb-000002
其中gi,r,c表示WINi中第r行第c列的信号值；δi,r,c为1时则gi,r,c为有效信号值，反之则为无效信号值；li,c表示WINi中第c列有效信号值的累加和。
根据式(3)计算各个有效窗中同列有效信号数目的和si,c；
Figure PCTCN2017071360-appb-000003
按式(4)计算每列有效信号的背景值，即用每个WINi中每列有效信号的平均值作为一个像素值进行加权平均，计算得到代表整幅图像当前列的背景值Dc，按式(5)计算得出背景参考值ref，即用代表整幅图像每列的背景值Dc求平均得到背景参考值ref，按式(6)计算得到第c列信号的补偿值Csc，根据线扫描 传感器特性，同一列的所有信号都是通过同一传感器点阵采集得到，所以可以用每列的背景值Dc与背景参考值ref之间的差异代表整幅图像该列所有像素的噪声干扰即补偿值Csc。如图6所示，计算得到的Dc波形与背景参考值ref偏差计算得到补偿值Csc，图6中纵坐标表示幅值，横坐标表示列坐标。
Figure PCTCN2017071360-appb-000004
Figure PCTCN2017071360-appb-000005
Csc＝ref-Dc            (6)
利用所得每列信号的补偿值Csc与原始信号值求和得到补偿信号，如式(7)，输出补偿成功后的信号f(r,c)，式中g(r,c)是各个位置的原始信号值。补偿后图像如图7所示，原有的异常亮条、暗条、chip线等干扰都可消除，且不存在干扰的区域不会受到影响。
f(r,c)＝g(r,c)+Csc             (7)
请参阅图8，本发明实施例还提供了一种图像补偿装置的第一个实施例，包括：
有效信号确定单元301，用于根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的有效窗计算出各有效窗对应的有效信号；
背景值单元302，用于根据计算出的有效信号进行原始信号对应的背景值的计算；
背景参考值单元303，根据背景值与预置参数计算窗的信息进行原始信号的背景参考值的计算；
补偿信号单元304，根据背景参考值与背景值确定原始信号对应的补偿信号。
上面是对纸图像补偿装置的单元进行详细的描述，下面将对图像补偿装置的单元下面的子单元进行详细的描述，请参阅图9，本发明实施例中提供的一种图像补偿装置的第二个实施例，包括：
有效信号确定单元401，用于根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的有效窗计算出各有效窗对应的有效信号；
背景值单元402，用于根据计算出的有效信号进行原始信号对应的背景值的计算；
背景参考值单元403，根据背景值与预置参数计算窗进行原始信号的背景参考值的计算；
补偿信号单元404，根据背景参考值与背景值确定原始信号对应的补偿信号。
有效信号确定单元401包括初始化子单元4011、重采样阈值计算子单元4012、有效窗判断子单元4013、有效信号判断子单元4014；
初始化子单元4011，用于获取扫描图像的原始信号，创建并初始化参数计算窗；
重采样阈值计算子单元4012，用于通过参数计算窗的所有灰度等级包含的数据量及数据量在参数计算窗的占比计算出重采样阈值；
有效窗判断子单元4013，用于对重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗；
有效信号判断子单元4014，用于确定有效窗中在重采样阈值范围内的信号为有效信号，否则为无效信号。
背景值单元402包括有效信号计算子单元4021和背景值计算子单元4022；
有效信号计算子单元4021，用于获取各个有效窗每列有效信号的数目以及每列有效信号的累加和；
背景值计算子单元4022，用于计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值。
背景参考值单元403具体用于将原始信号每列的背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个原始信号的背景参考值。
补偿信号单元404包括补偿值计算子单元4041和补偿信号输出子单元 4042；
补偿值计算子单元4041，用于把整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值；
补偿信号输出子单元4042，用于将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
本实施例中，首先初始化子单元4011获取扫描图像的原始信号，创建并初始化参数计算窗，然后重采样阈值计算子单元4012通过参数计算窗的所有灰度等级包含的数据量及数据量在参数计算窗的占比计算出重采样阈值，之后有效窗判断子单元4013对重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗，进而有效信号判断子单元4014确定有效窗中在重采样阈值范围内的信号为有效信号，否则为无效信号，之后有效信号计算子单元4021获取各个有效窗每列有效信号的数目以及每列有效信号的累加和，背景值计算子单元4022计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值，背景参考值单元403将原始信号每列的背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个原始信号的背景参考值，补偿值计算子单元4041用整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值，最后补偿信号输出子单元4042将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种图像补偿方法，其特征在于，包括：
    根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号；
    根据计算出的所述有效信号进行所述原始信号对应的背景值的计算；
    根据所述背景值与所述预置参数计算窗的信息进行所述原始信号的背景参考值的计算；
    根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号。
  2. 根据权利要求1所述的图像补偿方法，其特征在于，根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号具体为：
    获取扫描图像的原始信号，创建并初始化参数计算窗；
    通过所述参数计算窗的所有灰度等级包含的数据量及所述数据量在所述参数计算窗的占比计算出重采样阈值；
    对所述重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗；
    确定所述有效窗中在所述重采样阈值范围内的信号为有效信号，否则为无效信号。
  3. 根据权利要求1所述的图像补偿方法，其特征在于，根据计算出的所述有效信号进行所述原始信号对应的背景值的计算具体为：
    获取各个有效窗每列有效信号的数目以及每列有效信号的累加和；
    计算各个有效窗中同列有效信号累加和的和，然后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值。
  4. 根据权利要求1所述的图像补偿方法，其特征在于，根据所述背景值与所述预置参数计算窗的信息进行所述原始信号的背景参考值的计算具体为：
    将所述原始信号每列的所述背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个所述原始信号的背景参考值。
  5. 根据权利要求1所述的图像补偿方法，其特征在于，根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号具体为：
    用整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值；
    将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
  6. 一种图像补偿装置，其特征在于，包括：
    有效信号确定单元，用于根据获取到的扫描图像的原始信号所确定的预置参数计算窗进行有效窗的确定，并根据确定的所述有效窗计算出各所述有效窗对应的有效信号；
    背景值单元，用于根据计算出的所述有效信号进行所述原始信号对应的背景值的计算；
    背景参考值单元，根据所述背景值与所述预置参数计算窗的信息进行所述原始信号的背景参考值的计算；
    补偿信号单元，根据所述背景参考值与所述背景值确定所述原始信号对应的补偿信号。
  7. 根据权利要求6所述的图像补偿装置，其特征在于，所述有效信号确定单元包括初始化子单元、重采样阈值计算子单元、有效窗判断子单元、有效信号判断子单元；
    所述初始化子单元，用于获取扫描图像的原始信号，创建并初始化参数计算窗；
    所述重采样阈值计算子单元，用于通过所述参数计算窗的所有灰度等级包含的数据量及所述数据量在所述参数计算窗的占比计算出重采样阈值；
    所述有效窗判断子单元，用于对所述重采样阈值进行判断，若重采样阈值在预置范围内，则该参数计算窗为有效窗，否则为无效窗；
    所述有效信号判断子单元，用于确定所述有效窗中在所述重采样阈值范围内的信号为有效信号，否则为无效信号。
  8. 根据权利要求6所述的图像补偿装置，其特征在于，所述背景值单元包括有效信号计算子单元和背景值计算子单元；
    所述有效信号计算子单元，用于获取各个有效窗每列有效信号的数目以及每列有效信号的累加和；
    背景值计算子单元，用于计算各个有效窗中同列有效信号累加和的和，然 后除以各个有效窗中同列有效信号数目的和，将商代表原始信号该列的背景值。
  9. 根据权利要求6所述的图像补偿装置，其特征在于，所述背景参考值单元具体用于将所述原始信号每列的所述背景值求和然后除以预置的参数计算窗的宽度，将得出的商作为整个所述原始信号的背景参考值。
  10. 根据权利要求6所述的图像补偿装置，其特征在于，所述补偿信号单元包括补偿值计算子单元和补偿信号输出子单元；
    所述补偿值计算子单元，用于把整个信号的背景参考值减去原始信号每列背景值表示该列的补偿值；
    所述补偿信号输出子单元，用于将每列的补偿值与所有与其同列的信号求和得到补偿信号，输出保存补偿后的信号。
PCT/CN2017/071360 2016-09-20 2017-01-17 一种图像补偿方法和装置 Ceased WO2018053977A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610836702.2 2016-09-20
CN201610836702.2A CN106412380B (zh) 2016-09-20 2016-09-20 一种图像补偿方法和装置

Publications (1)

Publication Number Publication Date
WO2018053977A1 true WO2018053977A1 (zh) 2018-03-29

Family

ID=57997125

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/071360 Ceased WO2018053977A1 (zh) 2016-09-20 2017-01-17 一种图像补偿方法和装置

Country Status (2)

Country Link
CN (1) CN106412380B (zh)
WO (1) WO2018053977A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106412380B (zh) * 2016-09-20 2019-09-10 广州广电运通金融电子股份有限公司 一种图像补偿方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010220092A (ja) * 2009-03-18 2010-09-30 Ricoh Co Ltd 画像読取装置および画像形成装置
CN102473293A (zh) * 2009-08-07 2012-05-23 株式会社理光 图像处理设备、图像处理方法、以及计算机程序
CN103310528A (zh) * 2013-07-08 2013-09-18 广州广电运通金融电子股份有限公司 图像补偿修正方法及识别验钞装置
CN103942761A (zh) * 2014-04-23 2014-07-23 威海华菱光电股份有限公司 图像校正方法和装置
CN106412380A (zh) * 2016-09-20 2017-02-15 广州广电运通金融电子股份有限公司 一种图像补偿方法和装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100003459A (ko) * 2008-07-01 2010-01-11 삼성모바일디스플레이주식회사 유기전계 발광 표시장치 및 그 구동방법
CN101924855B (zh) * 2010-08-11 2012-05-16 中科院成都信息技术有限公司 灰度线阵扫描图像的修正方法
CN103108107A (zh) * 2013-03-05 2013-05-15 广州广电运通金融电子股份有限公司 图像处理装置及其图像数据校正方法
JP6001010B2 (ja) * 2014-06-11 2016-10-05 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010220092A (ja) * 2009-03-18 2010-09-30 Ricoh Co Ltd 画像読取装置および画像形成装置
CN102473293A (zh) * 2009-08-07 2012-05-23 株式会社理光 图像处理设备、图像处理方法、以及计算机程序
CN103310528A (zh) * 2013-07-08 2013-09-18 广州广电运通金融电子股份有限公司 图像补偿修正方法及识别验钞装置
CN103942761A (zh) * 2014-04-23 2014-07-23 威海华菱光电股份有限公司 图像校正方法和装置
CN106412380A (zh) * 2016-09-20 2017-02-15 广州广电运通金融电子股份有限公司 一种图像补偿方法和装置

Also Published As

Publication number Publication date
CN106412380A (zh) 2017-02-15
CN106412380B (zh) 2019-09-10

Similar Documents

Publication Publication Date Title
CN103369209B (zh) 视频降噪装置及方法
CN102693426B (zh) 一种图像显著区域检测方法
CN103353985B (zh) 一种图像高斯模糊的测度方法
US7995108B2 (en) Image processing apparatus, image processing program, electronic camera, and image processing method for image analysis of magnification chromatic aberration
CN109993797B (zh) 门窗位置检测方法及装置
US9202261B2 (en) Image processing apparatus and method
CN105279772B (zh) 一种红外序列图像的可跟踪性判别方法
JP7228341B2 (ja) 画像処理装置、画像処理方法、及び画像処理プログラム
RU2644513C1 (ru) Способ детектирования голографических элементов в видеопотоке
CN110345875B (zh) 标定及测距方法、装置、电子设备及计算机可读存储介质
CN107330891B (zh) 一种有效的图像质量评价系统
US20130237829A1 (en) Methods and systems for color flow dynamic frame persistence
CN116051421B (zh) 基于多维度的内窥镜图像质量评价方法、装置、设备及介质
WO2019123554A1 (ja) 画像処理装置、画像処理方法、及び、記録媒体
CN117036345A (zh) 一种压接导线的对边距测量方法及系统
JP5292886B2 (ja) 画像解析装置、その方法、プログラムおよび記録媒体
CN117475154A (zh) 一种基于优化Canny边缘检测的仪表图像识别方法及系统
WO2018053977A1 (zh) 一种图像补偿方法和装置
CN119152525B (zh) 一种基于ai视觉的透明瓶体曲面印刷图形文字检测系统
CN119359856B (zh) 一种高光谱遥感地质测绘控制系统及方法
JP2010250387A (ja) 画像認識装置、及びプログラム
US11113815B2 (en) Video processing methods and software architectures for analyzing transformation in objects
JP2019045990A (ja) 画像処理装置、画像処理方法、およびプログラム
KR100468858B1 (ko) 영상의 잡음 수준 추정 장치 및 방법
CN108171658B (zh) 检测伽马校正的方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17852057

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 18/07/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17852057

Country of ref document: EP

Kind code of ref document: A1